ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Struski, Łukasz, Rymarczyk, Dawid, Lewicki, Arkadiusz, Sabiniewicz, Robert, Tabor, Jacek, Zieliński, Bartosz
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909134336557056
author Struski, Łukasz
Rymarczyk, Dawid
Lewicki, Arkadiusz
Sabiniewicz, Robert
Tabor, Jacek
Zieliński, Bartosz
author_facet Struski, Łukasz
Rymarczyk, Dawid
Lewicki, Arkadiusz
Sabiniewicz, Robert
Tabor, Jacek
Zieliński, Bartosz
contents Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those predictions to obtain a bag label. The most common MIL model is when we consider a bag as positive if at least one of its instances has a positive label. However, this reasoning does not hold in many real-life scenarios, where the positive bag label is often a consequence of a certain percentage of positive instances. To address this issue, we introduce a dedicated instance-based method called ProMIL, based on deep neural networks and Bernstein polynomial estimation. An important advantage of ProMIL is that it can automatically detect the optimal percentage level for decision-making. We show that ProMIL outperforms standard instance-based MIL in real-world medical applications. We make the code available.
format Preprint
id arxiv_https___arxiv_org_abs_2306_10535
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging
Struski, Łukasz
Rymarczyk, Dawid
Lewicki, Arkadiusz
Sabiniewicz, Robert
Tabor, Jacek
Zieliński, Bartosz
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those predictions to obtain a bag label. The most common MIL model is when we consider a bag as positive if at least one of its instances has a positive label. However, this reasoning does not hold in many real-life scenarios, where the positive bag label is often a consequence of a certain percentage of positive instances. To address this issue, we introduce a dedicated instance-based method called ProMIL, based on deep neural networks and Bernstein polynomial estimation. An important advantage of ProMIL is that it can automatically detect the optimal percentage level for decision-making. We show that ProMIL outperforms standard instance-based MIL in real-world medical applications. We make the code available.
title ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2306.10535